Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4167 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5146. Min Range: -2.5146

Max Act: 2.5074. Min Act: -0.0000

Data Index: 248235 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 2.5146. Min Range: -2.5146

Max Act: 2.5146. Min Act: -0.0000

Data Index: 895906 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 2.5146. Min Range: -2.5146

Max Act: 2.3437. Min Act: -0.0000

Data Index: 1343137 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 2.5146. Min Range: -2.5146

Max Act: 2.4496. Min Act: -0.0000

Data Index: 185984 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 2.5146. Min Range: -2.5146

Max Act: 2.3252. Min Act: -0.0000

Data Index: 864043 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 2.5146. Min Range: -2.5146

Max Act: 1.8169. Min Act: -0.0000

Data Index: 397821 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 2.5146. Min Range: -2.5146

Max Act: 1.6815. Min Act: -0.0000

Data Index: 645655 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 2.5146. Min Range: -2.5146

Max Act: 1.5959. Min Act: -0.0000

Data Index: 725834 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 2.5146. Min Range: -2.5146

Max Act: 1.4989. Min Act: -0.0000

Data Index: 687263 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 2.5146. Min Range: -2.5146

Max Act: 1.3726. Min Act: -0.0000

Data Index: 197795 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 2.5146. Min Range: -2.5146

Max Act: 1.4106. Min Act: -0.0000

Data Index: 1220732 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 2.5146. Min Range: -2.5146

Max Act: 1.4132. Min Act: -0.0000

Data Index: 1255652 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 2.5146. Min Range: -2.5146

Max Act: 1.3130. Min Act: -0.0000

Data Index: 1124407 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 2.5146. Min Range: -2.5146

Max Act: 1.4541. Min Act: -0.0000

Data Index: 117693 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 2.5146. Min Range: -2.5146

Max Act: 1.3201. Min Act: -0.0000

Data Index: 1217808 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 2.5146. Min Range: -2.5146

Max Act: 1.3202. Min Act: -0.0000

Data Index: 85252 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 2.5146. Min Range: -2.5146

Max Act: 1.2881. Min Act: -0.0000

Data Index: 531797 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 2.5146. Min Range: -2.5146

Max Act: 1.3398. Min Act: -0.0000

Data Index: 384265 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 2.5146. Min Range: -2.5146

Max Act: 1.2931. Min Act: -0.0000

Data Index: 428807 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 2.5146. Min Range: -2.5146

Max Act: 1.2007. Min Act: -0.0000

Data Index: 192169 (C4 (Web Text))

Max Activating Token Index: 1007